Presentation 2007-06-15
Self-Organizing Model of Information Separation by Distributed Representation : Dedicated to the late Dr. Koji Wada
Ryuichi Kimura, Koji Kurata,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a self-organizing model of information separation by distributed representation. This model can map two information components separately into two self-organizing layers which are connected- by anti-Hebbian inhibitory connections. Anti-Hebbian inhibitory connections make the activation of the two layers statistically independent. Distributed representation allows larger number of codes than winner-take-all representation with a same number of neurons.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) distributed representation / Self-Organizing Model / Information Separation / activation pattern / Anti-Hebbian inhibitory connection
Paper # NC2007-24
Date of Issue

Conference Information
Committee NC
Conference Date 2007/6/7(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Self-Organizing Model of Information Separation by Distributed Representation : Dedicated to the late Dr. Koji Wada
Sub Title (in English)
Keyword(1) distributed representation
Keyword(2) Self-Organizing Model
Keyword(3) Information Separation
Keyword(4) activation pattern
Keyword(5) Anti-Hebbian inhibitory connection
1st Author's Name Ryuichi Kimura
1st Author's Affiliation Faculty of Engineering, University of the Ryukyus()
2nd Author's Name Koji Kurata
2nd Author's Affiliation Faculty of Engineering, University of the Ryukyus
Date 2007-06-15
Paper # NC2007-24
Volume (vol) vol.107
Number (no) 92
Page pp.pp.-
#Pages 6
Date of Issue